fine_tuned_t5_small_model_sec_5_v13

README.md

@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7774
-- Rouge1: 0.4108
-- Rouge2: 0.1781
-- Rougel: 0.2726
-- Rougelsum: 0.2718
-- Gen Len: 92.0632
-- Bert F1: 0.8798
+- Loss: 2.9991
+- Rouge1: 0.4046
+- Rouge2: 0.1585
+- Rougel: 0.2567
+- Rougelsum: 0.2569
+- Gen Len: 94.9263
+- Bert F1: 0.8757
 
 ## Model description
 
@@ -49,20 +49,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 15
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bert F1 |
-|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:-------:|
-| 3.3874        | 2.1053  | 200  | 2.8941          | 0.4202 | 0.1821 | 0.2711 | 0.2709    | 96.7632 | 0.8794  |
-| 3.0816        | 4.2105  | 400  | 2.8326          | 0.4123 | 0.179  | 0.2691 | 0.2695    | 92.4579 | 0.88    |
-| 3.0216        | 6.3158  | 600  | 2.8048          | 0.4129 | 0.1809 | 0.2722 | 0.272     | 90.7368 | 0.8804  |
-| 2.9749        | 8.4211  | 800  | 2.7914          | 0.4094 | 0.1786 | 0.272  | 0.2714    | 90.1526 | 0.8804  |
-| 2.9656        | 10.5263 | 1000 | 2.7815          | 0.4105 | 0.1789 | 0.2714 | 0.2709    | 91.6474 | 0.8798  |
-| 2.9433        | 12.6316 | 1200 | 2.7794          | 0.4099 | 0.1771 | 0.2712 | 0.2704    | 92.2211 | 0.8797  |
-| 2.9274        | 14.7368 | 1400 | 2.7774          | 0.4108 | 0.1781 | 0.2726 | 0.2718    | 92.0632 | 0.8798  |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bert F1 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:-------:|
+| 3.5483        | 1.0   | 95   | 3.1402          | 0.409  | 0.1649 | 0.2588 | 0.2594    | 97.2947 | 0.8751  |
+| 3.1867        | 2.0   | 190  | 3.0364          | 0.4075 | 0.1591 | 0.2556 | 0.2558    | 97.8263 | 0.8754  |
+| 3.1221        | 3.0   | 285  | 3.0062          | 0.407  | 0.1599 | 0.2569 | 0.2572    | 95.0579 | 0.8759  |
+| 3.0951        | 4.0   | 380  | 2.9991          | 0.4046 | 0.1585 | 0.2567 | 0.2569    | 94.9263 | 0.8757  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c530ede872d8f88ddbfb1906e7bab0cd67868fa3b35371a12024557c563b0e2f
+oid sha256:49c6b7bb20bfcf17ef7f84c6a0cee5dc4ffbe490923b1e1eb9ee196ac82dcae1
 size 242041896

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0fd6016ffbd53168d9474c781f93e1d9f8a96a85b79a474cc9be789188dc4b
+oid sha256:87dec8142832d629bd25f5cbd6fa2c0fc0a7b71835c096358baf0394de32b233
 size 5368